Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2115 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.6016. Min Act: 0.0000

Data Index: 1591480 (The Pile)

Max Activating Token Index: 259

Text #1

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1551495 (The Pile)

Max Activating Token Index: 329

Text #2

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1330585 (The Pile)

Max Activating Token Index: 995

Text #3

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4626. Min Act: -0.0000

Data Index: 472051 (The Pile)

Max Activating Token Index: 313

Text #4

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4698. Min Act: -0.0000

Data Index: 169203 (The Pile)

Max Activating Token Index: 142

Text #5

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4212. Min Act: -0.0000

Data Index: 1242418 (The Pile)

Max Activating Token Index: 989

Text #6

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1043754 (The Pile)

Max Activating Token Index: 338

Text #7

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1980835 (The Pile)

Max Activating Token Index: 290

Text #8

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1024900 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.3723. Min Act: -0.0000

Data Index: 445735 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.3917. Min Act: -0.0000

Data Index: 840886 (The Pile)

Max Activating Token Index: 827

Text #11

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.3777. Min Act: 0.0000

Data Index: 1291202 (The Pile)

Max Activating Token Index: 151

Text #12

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4172. Min Act: -0.0000

Data Index: 708159 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.3790. Min Act: -0.0000

Data Index: 413469 (The Pile)

Max Activating Token Index: 274

Text #14

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.3855. Min Act: -0.0000

Data Index: 891153 (The Pile)

Max Activating Token Index: 550

Text #15

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1217977 (The Pile)

Max Activating Token Index: 940

Text #16

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.3766. Min Act: -0.0000

Data Index: 489888 (The Pile)

Max Activating Token Index: 952

Text #17

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1139261 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1360864 (The Pile)

Max Activating Token Index: 382

Text #19

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.3644. Min Act: -0.0000

Data Index: 17542 (The Pile)

Max Activating Token Index: 796